Mafin 2.5 achieves 98.7% accuracy in FinanceBench by changing the retrieval query.

AIMPACT News, May 4th (UTC+8), Vectorless RAG improves retrieval accuracy by removing the vector database. The PageIndex style system changes the traditional retrieval logic, no longer asking “which text block is closest to the query,” but directly locating “where the answer is in the document.” This change allows the Mafin 2.5 system to achieve a 98.7% accuracy rate on the FinanceBench benchmark, and this achievement is not dependent on better embedding models but results from the change in retrieval primitives. Traditional vector RAG systems have inherent limitations when handling complex nested queries (such as “Operating income for Q3 2024 excluding restructuring costs”) and precise numerical queries, which is the core reason why Vectorless RAG can achieve more accurate retrievals.